Projects:InteractiveSegmentation - Revision history

Ygao at 01:03, 16 November 2013

2013-11-16T01:03:26Z

Tannenba: /* Key Investigators */

2011-10-17T19:51:18Z

Key Investigators

Ivan.kolesov at 18:19, 17 October 2011

2011-10-17T18:19:20Z

Ivan.kolesov at 17:14, 17 October 2011

2011-10-17T17:14:01Z

Ivan.kolesov at 17:13, 17 October 2011

2011-10-17T17:13:48Z

Ivan.kolesov at 17:10, 17 October 2011

2011-10-17T17:10:57Z

Ivan.kolesov at 17:10, 17 October 2011

2011-10-17T17:10:36Z

Ivan.kolesov at 17:10, 17 October 2011

2011-10-17T17:10:18Z

Ivan.kolesov at 16:56, 17 October 2011

2011-10-17T16:56:19Z

Ivan.kolesov at 16:51, 17 October 2011

2011-10-17T16:51:50Z

@@ Line 1: / Line 1: @@
-  Back to [[Algorithm:BU|Boston University Algorithms]]
+  Back to [[Algorithm:Stony Brook|Stony Brook University Algorithms]]
 __NOTOC__
 = Interactive Image Segmentation With Active Contours =

@@ Line 21: / Line 21: @@
 = Key Investigators =
-* Georgia Tech: Ivan Kolesov, Peter Karasev, Karol Chudy, and Allen Tannenbaum
 * Emory University: Grant Muller and John Xerogeanes

@@ Line 17: / Line 17: @@
 == Current State of Work ==
-We have gathered a sample data set; currently, we are registering the scan to create a united patient model. This model will localize structures and constrain shape. Additionally, we are investigation interaction approaches for registration and segmentation that will "put the user in the loop" but greatly reduce the work compared to manual approaches.
+The described algorithm is implemented in c++ and delivered to physicians. We have begun to analyze the data they created by segmenting the knee with out tool. Future work incorporates shape prior into the segmentation and improves user interaction(according to feedback physician's provide us).
 = Key Investigators =

← Older revision		Revision as of 17:14, 17 October 2011
Line 6:		Line 6:

	= Description =		= Description =
−	In this work, interactive segmentation is integrated with an active contour model and segmentation is posed as a human-supervisory control problem. User input is tightly coupled with an automatic segmentation algorithm leveraging the user's high-level anatomical knowledge and the automated method's speed. Real-time visualization enables the user to quickly identify and correct the result in a sub-domain where the variational model's statistical assumptions do not agree with his expert knowledge. Methods developed in this work are applied to magnetic resonance imaging (MRI) volumes as part of a population study of human skeletal development. Segmentation time is reduced by approximately ~~five�~~ times over similarly accurate manual segmentation of large bone structures.	+	In this work, interactive segmentation is integrated with an active contour model and segmentation is posed as a human-supervisory control problem. User input is tightly coupled with an automatic segmentation algorithm leveraging the user's high-level anatomical knowledge and the automated method's speed. Real-time visualization enables the user to quickly identify and correct the result in a sub-domain where the variational model's statistical assumptions do not agree with his expert knowledge. Methods developed in this work are applied to magnetic resonance imaging (MRI) volumes as part of a population study of human skeletal development. Segmentation time is reduced by approximately five times over similarly accurate manual segmentation of large bone structures.

@@ Line 3: / Line 3: @@
 = Interactive Image Segmentation With Active Contours =
-Proton therapy is used to deliver accurate doses of radiation to people undergoing cancer treatment. At the beginning of treatment, a personalized plan describing the amount of radiation and location to which it must be delivered is created for the patient. However, over the course of the treatment, which lasts weeks, a person's anatomy is likely to change. Adaptive radiotherapy aims to improve fractionated radiotherapy by re-optimizing the radiation treatment plan for each session. To update the plan, the CT images acquired during a treatment session are registered to the treatment plan and doses of radiation to be delivered are re-calculated accordingly. Registering a patient scan to a model (ex.Atlas) provides important prior information for a segmentation algorithm and in the other direction, having segmentation of a structure, can be used for better registration; hence, segmentation and registration must be done concurrently.
+A driving clinical study for the present work is a population study of skeletal development in youth. Bone grows from the physis (growth plate), located in the middle of a long bone between the epiphysis and metaphysis. Full adult growth is reached when the physis disappears completely. Precise understanding of how the growth plates in femur and tibia change from childhood to adulthood enables improved surgical planning(e.g. determining tunnel placement for anterior cruciate ligament (ACL) reconstruction) to avoid stunting the patient's growth or compromising the stability of the knee. Currently, growth potential is measured by a physician using an x-ray scan of multiple bones; patients receive repeated doses of radiation exposure.
 = Description =
 * [[Image:KSliceFlowChart.png | Rel Pred| 800px]]

@@ Line 10: / Line 10: @@
 * [[Image:KSliceFlowChart.png | Rel Pred| 800px]]
- Flowchart for the interactive segmentation approach. Notice the user's pivotal role in the process.
+Flowchart for the interactive segmentation approach. Notice the user's pivotal role in the process.
 * [[Image:KSliceInptTimeChart.png | Eye Seg| 800px]]
 Time-line of user input into the system. Note that user input is sparse, has local effect only, and decreases in frequency and magnitude over time.

@@ Line 9: / Line 9: @@
 Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.
-* [[Image:KSliceFlowChart.png | Rel Pred| 400x]] Flowchart for the interactive segmentation approach. Notice the user's pivotal role in the process.
+* [[Image:KSliceFlowChart.png | Rel Pred| 800px]]
-* [[Image:KSliceInptTimeChart.png | Eye Seg| 400px]] Time-line of user input into the system. Note that user input is sparse, has local effect only, and decreases in frequency and magnitude over time.
+ Flowchart for the interactive segmentation approach. Notice the user's pivotal role in the process.
-* [[Image:KVoutSegTightMod.png | Eye Seg| 500px]] Time-line of user input into the system. Note that user input is sparse, has local effect only, and decreases in frequency and magnitude over time.
+* [[Image:KSliceInptTimeChart.png | Eye Seg| 800px]] T
 == Current State of Work ==

@@ Line 9: / Line 9: @@
 Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.
-* [[Image:Model3D_upTrans.png | Rel Pred| 250px]] Prediction of mandible location(red) give a brainstem(yellow) and larynx(blue) segmentation; ground truth segmenation is green.
+* [[Image:KSliceFlowChart.png | Rel Pred| 250px]] Flowchart for the interactive segmentation approach. Notice the user's pivotal role in the process.
-* [[Image:3D_eye.png | Eye Seg| 250px]] Segmentation of the eye ball.
+* [[Image:KSliceInptTimeChart.png | Eye Seg| 250px]] Time-line of user input into the system. Note that user input is sparse, has local effect only, and decreases in frequency and magnitude over time.